CHEN, J.; XUN, Z.; ZHOU, B.; QI, H.; ZHANG, H.; ZHANG, Q.; CHEN, Y.; HU, W.; QU, Y.; HU, S. Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 24, p. 20083-20091, 2026. DOI: 10.1609/aaai.v40i24.39094. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39094. Acesso em: 3 may. 2026.